FedTGP: Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive Learning for Data and Model Heterogeneity in Federated Learning.
Jianqing ZhangYang LiuYang HuaJian CaoPublished in: AAAI (2024)
Keyphrases
- prior knowledge
- learning process
- learning phase
- experimental data
- learning systems
- social networks
- linear predictors
- accurate models
- sensory data
- learning models
- mathematical model
- knowledge acquisition
- online learning
- learning algorithm
- data collection
- data processing
- supervised learning
- test data
- data sources
- learning mechanism
- active learning
- learned models
- data structure
- reinforcement learning